Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.4128. Min Act: -0.1700
Data Index: 2428377 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.4128. Min Act: -0.1700
Data Index: 5947352 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3815. Min Act: -0.1700
Data Index: 3786003 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3815. Min Act: -0.1700
Data Index: 7252556 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3815. Min Act: -0.1700
Data Index: 6902614 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3815. Min Act: -0.1700
Data Index: 4244101 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3815. Min Act: -0.1700
Data Index: 72918 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3815. Min Act: -0.1700
Data Index: 4953468 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3815. Min Act: -0.1700
Data Index: 1636595 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3503. Min Act: -0.1700
Data Index: 3549236 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3503. Min Act: -0.1699
Data Index: 6901419 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3503. Min Act: -0.1700
Data Index: 5905181 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3503. Min Act: -0.1700
Data Index: 3304060 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3190. Min Act: -0.1700
Data Index: 824824 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3503. Min Act: -0.1700
Data Index: 4986661 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3190. Min Act: -0.1700
Data Index: 2871324 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3190. Min Act: -0.1700
Data Index: 2428378 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3503. Min Act: -0.1700
Data Index: 4955531 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3503. Min Act: -0.1700
Data Index: 415823 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3503. Min Act: -0.1700
Data Index: 407307 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19